Installing and training UNITE fungal ITS classifier

I am currently trying to install a classifier into QIIME and when I follow the instructions i get an error code;

​/tmp/qiime2-q2cli-err-xkxb4y77.log: line 1: `/home/ubuntu/miniconda3/envs/qiime2-2021.8/lib/python3.8/site-packages/q2_feature_classifier/classifier.py:102: UserWarning: The TaxonomicClassifier artifact that results from this method was trained using scikit-learn version 0.24.1. It cannot be used with other versions of scikit-learn. (While the classifier may complete successfully, the results will be unreliable.)'

conda list scikit
scikit-bio 0.5.6 py38h0b5ebd8_4 conda-forge
scikit-learn 0.24.1 py38h658cfdd_0 conda-forge

Just trying to figure out how to get past this considering that I'm using 0.24.1. PSA i am very new to bioinformatics so please provide answers as if i know nothing. TIA

FYI MY CODE
(qiime2-2021.8) ubuntu@fungi:~$ qiime feature-classifier fit-classifier-naive-bayes \

--i-reference-reads rep-seqs.qza
--i-reference-taxonomy ref-taxonomy.qza
--o-classifier classifier.qza

​OUTPUT
Plugin error from feature-classifier:

not enough values to unpack (expected 2, got 0)

Debug info has been saved to /tmp/qiime2-q2cli-err-xkxb4y77.log

@Declan-Swin,

The UserWarning is just that, a warning so that you are aware that you do not try to use the warning with other versions of scikit-learn, so I think you are good there :slightly_smiling_face:

Regarding the errors that you are getting, it looks like you are following along with the tutorial and that you have specified rep-seqs.qza for --i-reference-reads instead of ref-seqs.qza.

rep-seqs.qza is there to check the classifier against. The ref-seqs.qza contains the reference sequences that you extract out of the 85_otus.qza in the preceding step. You could just as easily use the 85_otus.qza to run fit-classifier-naive-bayes, though you would end up with a less accurate output. Try running it again with:

qiime feature-classifier fit-classifier-naive-bayes
--i-reference-reads ref-seqs.qza
--i-reference-taxonomy ref-taxonomy.qza
--o-classifier classifier.qza

Finally, since you say that you are training a UNITE fungal ITS classifier, I would not extract reads before running fit-classifier-naive-bayes. See this section of the tutorial for the explanation.

Hope this helps!

This topic was automatically closed 31 days after the last reply. New replies are no longer allowed.